BriefGPT.xyz
Apr, 2016
LSTM-CF: 基于LSTM的RGB-D场景标记中上下文建模和融合的统一
RGB-D Scene Labeling with Long Short-Term Memorized Fusion Model
HTML
PDF
Zhen Li, Yukang Gan, Xiaodang Liang, Yizhou Yu, Hui Cheng...
TL;DR
本文开发了一种新型的LSTM-CF模型,它可以从多个光度和深度数据通道捕获和融合上下文信息,并将此模型纳入深度卷积神经网络(CNNs),以用于端到端训练,以提高细粒度语义标签的准确性。
Abstract
semantic labeling
of
rgb-d scenes
is crucial to many intelligent applications including perceptual robotics. It generates pixelwise and fine-grained label maps from simultaneously sensed photometric (RGB) and dep
→